SOTAVerified

RAG

Retrieval-Augmented Generation (RAG) is a task that combines the strengths of both retrieval-based models and generation-based models. In this approach, a retrieval system selects relevant documents or passages from a large corpus, and a generation model, typically a neural language model, uses the retrieved information to generate a response. This method enhances the accuracy and coherence of generated text, especially in tasks requiring detailed knowledge or long context handling.

RAG is particularly useful in open-domain question answering, knowledge-grounded dialogue, and summarization tasks. The retrieval step helps the model to access and incorporate external information, making it less reliant on memorized knowledge and better suited for generating responses based on the latest or domain-specific information.

The performance of RAG systems is usually measured using metrics such as precision, recall, F1 score, BLEU score, and exact match. Some popular datasets for evaluating RAG models include Natural Questions, MS MARCO, TriviaQA, and SQuAD.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1451–1500 of 2111 papers

TitleStatusHype
MARAGS: A Multi-Adapter System for Multi-Task Retrieval Augmented Generation Question Answering—0
MoA is All You Need: Building LLM Research Team using Mixture of Agents—0
Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering—0
Creating a Gen-AI based Track and Trace Assistant MVP (SuperTracy) for PostNL—0
NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for RetrievalCode1
Language Model Powered Digital Biology with BRADCode2
GenDFIR: Advancing Cyber Incident Timeline Analysis Through Retrieval Augmented Generation and Large Language Models—0
You Only Use Reactive Attention Slice For Long Context RetrievalCode0
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical StudyCode0
In Defense of RAG in the Era of Long-Context Language Models—0
BEAVER: An Enterprise Benchmark for Text-to-SQL—0
AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models—0
Benchmarking Cognitive Domains for LLMs: Insights from Taiwanese Hakka Culture—0
Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&ACode0
A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine—0
The Design of an LLM-powered Unstructured Analytics System—0
GenAI-powered Multi-Agent Paradigm for Smart Urban Mobility: Opportunities and Challenges for Integrating Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) with Intelligent Transportation Systems—0
OrthoDoc: Multimodal Large Language Model for Assisting Diagnosis in Computed Tomography—0
MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language ModelsCode0
RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance—0
HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications—0
Conan-embedding: General Text Embedding with More and Better Negative Samples—0
LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance PropagationCode3
Text2SQL is Not Enough: Unifying AI and Databases with TAGCode4
Writing in the Margins: Better Inference Pattern for Long Context RetrievalCode2
Probing Causality Manipulation of Large Language Models—0
Claim Verification in the Age of Large Language Models: A Survey—0
Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models—0
Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering—0
Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language ModelsCode0
Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMsCode0
LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction—0
GRATR: Zero-Shot Evidence Graph Retrieval-Augmented Trustworthiness ReasoningCode0
RAG-Optimized Tibetan Tourism LLMs: Enhancing Accuracy and Personalization—0
RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented GenerationCode3
Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP StandardsCode1
Xinyu: An Efficient LLM-based System for Commentary Generation—0
WeQA: A Benchmark for Retrieval Augmented Generation in Wind Energy Domain—0
A Quick, trustworthy spectral knowledge Q&A system leveraging retrieval-augmented generation on LLMCode0
Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian PhilosophyCode0
Towardseffective teaching assistants: From intent-based chatbots to LLM-poweredteachingassistants—0
Reading with Intent—0
Reconciling Methodological Paradigms: Employing Large Language Models as Novice Qualitative Research Assistants in Talent Management Research—0
Enhanced document retrieval with topic embeddings—0
Carbon Footprint Accounting Driven by Large Language Models and Retrieval-augmented Generation—0
LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal DomainCode2
Agentic Retrieval-Augmented Generation for Time Series Analysis—0
TC-RAG:Turing-Complete RAG's Case study on Medical LLM SystemsCode2
VERA: Validation and Evaluation of Retrieval-Augmented Systems—0
Meta Knowledge for Retrieval Augmented Large Language Models—0
Show:102550
← PrevPage 30 of 43Next →

No leaderboard results yet.